模块化安全护栏是现实世界中由基础模型赋能的机器人所必需的
Modular Safety Guardrails Are Necessary for Foundation-Model-Enabled Robots in the Real World
AI总结：
本文提出模块化安全护栏以解决现实世界中由基础模型赋能的机器人在开放、长尾和随时间适应的环境中的安全挑战。
摘要：
将基础模型（FMs）整合到机器人中已经加速了现实世界的部署，但同时也引入了新的安全挑战，这些挑战源于开放语义推理和具身物理行动。这些挑战要求安全概念超越物理约束满足。在本文中，我们从三个维度 characterize FM-enabled 机器人安全：行动安全（物理可行性和约束合规性）、决策安全（语义和情境适当性）以及以人为本的安全（符合人类意图、规范和期望）。我们争论说现有方法，包括静态验证、单体控制器和端到端学习策略，在任务、环境和人类期望开放、长尾和随时间适应的设置中是不足的。为了解决这一差距，我们提出了模块化安全护栏，由监控（评估）和干预层组成，作为自主栈中全面安全的架构基础。除了模块化之外，我们通过表征对齐和保守主义分配突出可能的跨层协同设计机会，以实现更快、更不保守和更有效的安全执行。我们呼吁社区探索更丰富的护栏模块和原则性的协同设计策略，以推进安全的现实世界物理AI部署。
英文摘要：
The integration of foundation models (FMs) into robotics has accelerated real-world deployment, while introducing new safety challenges arising from open-ended semantic reasoning and embodied physical action. These challenges require safety notions beyond physical constraint satisfaction. In this paper, we characterize FM-enabled robot safety along three dimensions: action safety (physical feasibility and constraint compliance), decision safety (semantic and contextual appropriateness), and human-centered safety (conformance to human intent, norms, and expectations). We argue that existing approaches, including static verification, monolithic controllers, and end-to-end learned policies, are insufficient in settings where tasks, environments, and human expectations are open-ended, long-tailed, and subject to adaptation over time. To address this gap, we propose modular safety guardrails, consisting of monitoring (evaluation) and intervention layers, as an architectural foundation for comprehensive safety across the autonomy stack. Beyond modularity, we highlight possible cross-layer co-design opportunities through representation alignment and conservatism allocation to enable faster, less conservative, and more effective safety enforcement. We call on the community to explore richer guardrail modules and principled co-design strategies to advance safe real-world physical AI deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
